Iss23 (#24)

* Bumping version to v0.1.1 to add a minor feature of including NA values in printed stats * Adding feature to consider or not consider NA values in stats * adding NA values consideration feature * Updating long usage notice/message
CH-Earth · Feb 18, 2023 · f131743 · f131743
1 parent d0995ce
commit f131743
Show file tree

Hide file tree

Showing 10 changed files with 74 additions and 34 deletions.
diff --git a/README.md b/README.md
@@ -8,7 +8,8 @@ Usage:
 Script options:
   -d, --dataset				Geospatial dataset of interest, currently
                                         available options are: 'MODIS';
-                                        'MERIT-Hydro';'SoilGridsV1'
+                                        'MERIT-Hydro';'SoilGridsV1';'Landsat';
+					'gsde';'depth-to-bedrock';
   -i, --dataset-dir=DIR			The source path of the dataset file(s)
   -r, --crs=INT				The EPSG code of interest; optional
   					[defaults to 4326]
@@ -30,15 +31,17 @@ Script options:
 					'min';'max';'mean';'majority';'minority';
 					'median';'quantile';'variety';'variance';
 					'stdev';'coefficient_of_variation';'frac';
-					'coords'; optional
+					'coords'; 'count'; optional
+  -u, --include-na			Include NA values in generated statistics;
+  					optional 
   -q, --quantile=q1[,q2[...]]		Quantiles of interest to be produced if 'quantile'
   					is included in the '--stat' argument. The values
 					must be comma delimited float numbers between
 					0 and 1; optional [defaults to every 5th quantile]
   -p, --prefix=STR			Prefix  prepended to the output files
   -c, --cache=DIR			Path of the cache directory; optional
   -E, --email=STR			E-mail when job starts, ends, and 
-  					finishes; optional
+  					fails; optional
   -V, --version				Show version
   -h, --help				Show this screen and exit
 ```

diff --git a/VERSION b/VERSION
@@ -1 +1 @@
-0.1.0
+0.1.1
diff --git a/assets/stats.R b/assets/stats.R
@@ -31,7 +31,8 @@ vrt_path <- args[12];
 shapefile_path <- args[13];
 output_path <- args[14];
 stats <- args[15];
-quantiles <- args[16];
+include_na <- args[16];
+quantiles <- args[17];
 
 # set the working directory path
 setwd(working_dir_path)
@@ -75,11 +76,21 @@ if (coord_var %in% s) {
 } else {
   include_coords = FALSE
 }
+
 # extract ID column name
 id_col <- names(p[1])[1]
 
+# check `na_values`
+if (include_na == 'true') {
+  na_values = 9999
+  print('Including NA values');
+} else {
+  na_values = NA_real_
+  print('NOT including NA values');
+}
+
 # run exactextractr and calculate necessary stats
-df <- exactextractr::exact_extract(r, p, s, quantiles=q, append_cols=id_col); # assuming first column indicates ID
+df <- exactextractr::exact_extract(r, p, s, default_value=na_values, quantiles=q, append_cols=id_col); # assuming first column indicates ID
 
 # extract centroid coordinates and prepend to `df`
 if (include_coords == TRUE) {

diff --git a/depth_to_bedrock/depth_to_bedrock.sh b/depth_to_bedrock/depth_to_bedrock.sh
@@ -41,12 +41,12 @@
 # Usage Functions
 # ===============
 short_usage() {
-  echo "usage: $(basename $0) -cio DIR -v var1[,var2[...]] [-r INT] [-se DATE] [-ln REAL,REAL] [-f PATH] [-t BOOL] [-a stat1[,stat2,[...]] [-q q1[,q2[...]]]] [-p STR] "
+  echo "usage: $(basename $0) -cio DIR -v var1[,var2[...]] [-r INT] [-se DATE] [-ln REAL,REAL] [-f PATH] [-t BOOL] [-a stat1[,stat2,[...]] [-u BOOL] [-q q1[,q2[...]]]] [-p STR] "
 }
 
 
 # argument parsing using getopt - WORKS ONLY ON LINUX BY DEFAULT
-parsedArguments=$(getopt -a -n depth-to-bedrock -o i:o:v:r:s:e:l:n:f:t:a:q:p:c: --long dataset-dir:,output-dir:,variable:,crs:,start-date:,end-date:,lat-lims:,lon-lims:,shape-file:,print-geotiff:,stat:,quantile:,prefix:,cache: -- "$@")
+parsedArguments=$(getopt -a -n depth-to-bedrock -o i:o:v:r:s:e:l:n:f:t:a:u:q:p:c: --long dataset-dir:,output-dir:,variable:,crs:,start-date:,end-date:,lat-lims:,lon-lims:,shape-file:,print-geotiff:,stat:,include-na:,quantile:,prefix:,cache: -- "$@")
 validArguments=$?
 if [ "$validArguments" != "0" ]; then
   short_usage;
@@ -75,6 +75,7 @@ do
     -f | --shape-file)    shapefile="$2"       ; shift 2 ;; # required - could be redundant
     -t | --print-geotiff) printGeotiff="$2"    ; shift 2 ;; # required
     -a | --stat)	  stats="$2"	       ; shift 2 ;; # optional
+    -u | --include-na)	  includeNA="$2"       ; shift 2 ;; # required
     -q | --quantile)	  quantiles="$2"       ; shift 2 ;; # optional
     -p | --prefix)	  prefix="$2"          ; shift 2 ;; # optional
     -c | --cache)	  cache="$2"           ; shift 2 ;; # required
@@ -273,6 +274,7 @@ if [[ -n "$shapefile" ]] && [[ -n $stats ]]; then
 	    "$shapefile" \
 	    "$outputDir/${prefix}stats_${var}.csv" \
 	    "$stats" \
+	    "$includeNA" \
 	    "$quantiles" >> "${outputDir}/${prefix}stats_${var}.log" 2>&1;
   done
 fi

diff --git a/extract-gis.sh b/extract-gis.sh
@@ -36,15 +36,16 @@
 # Help functions
 # ==============
 usage () {
-  echo "GISTOOL: Geospatial Dataset Processing Script
+  echo "GISTOOL: Geospatial Data Processing Script
 
 Usage:
   extract-gis [options...]
 
 Script options:
   -d, --dataset				Geospatial dataset of interest, currently
                                         available options are: 'MODIS';
-                                        'MERIT-Hydro';'SoilGridsV1'
+                                        'MERIT-Hydro';'SoilGridsV1';'Landsat';
+					'gsde';'depth-to-bedrock';
   -i, --dataset-dir=DIR			The source path of the dataset file(s)
   -r, --crs=INT				The EPSG code of interest; optional
   					[defaults to 4326]
@@ -66,26 +67,28 @@ Script options:
 					'min';'max';'mean';'majority';'minority';
 					'median';'quantile';'variety';'variance';
 					'stdev';'coefficient_of_variation';'frac';
-					'coords'; optional
+					'coords'; 'count'; optional
+  -u, --include-na			Include NA values in generated statistics;
+  					optional 
   -q, --quantile=q1[,q2[...]]		Quantiles of interest to be produced if 'quantile'
   					is included in the '--stat' argument. The values
 					must be comma delimited float numbers between
 					0 and 1; optional [defaults to every 5th quantile]
   -p, --prefix=STR			Prefix  prepended to the output files
   -c, --cache=DIR			Path of the cache directory; optional
   -E, --email=STR			E-mail when job starts, ends, and 
-  					finishes; optional
+  					fails; optional
   -V, --version				Show version
   -h, --help				Show this screen and exit
 
-For bug reports, questions, discussions open an issue
+For bug reports, questions, and discussions open an issue
 at https://github.com/kasra-keshavarz/gistool/issues" >&1;
 
   exit 0;
 }
 
 short_usage () {
-  echo "usage: $(basename $0) -d DATASET -io DIR -v var1[,var2,[...]] [-jVhE] [-t BOOL] [-c DIR] [-se DATE] [-r INT] [-ln REAL,REAL] [-f PATH} [-p STR] [-a stat1[,stat2,[...]] [-q q1[,q2[...]]]] " >&1;
+  echo "usage: $(basename $0) -d DATASET -io DIR -v var1[,var2,[...]] [-jVhEu] [-t BOOL] [-c DIR] [-se DATE] [-r INT] [-ln REAL,REAL] [-f PATH] [-p STR] [-a stat1[,stat2,[...]] [-q q1[,q2[...]]]] " >&1;
 }
 
 version () {
@@ -107,8 +110,11 @@ shopt -s expand_aliases
 # =======================
 # Parsing input arguments
 # =======================
-# argument parsing using getopt - WORKS ONLY ON LINUX BY DEFAULT
-parsedArguments=$(getopt -a -n extract-geotiff -o d:i:r:v:o:s:e:l:n:f:jt:a:q:p:c:EVh --long dataset:,dataset-dir:,crs:,variable:,output-dir:,start-date:,end-date:,lat-lims:,lon-lims:,shape-file:,submit-job,print-geotiff:,stat:,quantile:,prefix:,cache:,email:,version,help -- "$@")
+# argument parsing using getopt - 
+# ATTENTION: `getopt` is available by default on most GNU/Linux 
+#	     distributions, however, it may not work out of the
+#	     box on MacOS or BSD
+parsedArguments=$(getopt -a -n extract-geotiff -o d:i:r:v:o:s:e:l:n:f:jt:a:uq:p:c:EVh --long dataset:,dataset-dir:,crs:,variable:,output-dir:,start-date:,end-date:,lat-lims:,lon-lims:,shape-file:,submit-job,print-geotiff:,stat:,include-na,quantile:,prefix:,cache:,email:,version,help -- "$@")
 validArguments=$?
 # check if there is no valid options
 if [ "$validArguments" != "0" ]; then
@@ -140,6 +146,7 @@ do
     -j | --submit-job)    jobSubmission=true   ; shift   ;; # optional
     -t | --print-geotiff) printGeotiff="$2"    ; shift 2 ;; # optional
     -a | --stat)	  stats="$2"	       ; shift 2 ;; # optional
+    -u | --include-na)	  includeNA=true       ; shift	 ;; # optional
     -q | --quantile)	  quantiles="$2"       ; shift 2 ;; # optional
     -p | --prefix)	  prefixStr="$2"       ; shift 2 ;; # required
     -c | --cache)	  cache="$2"	       ; shift 2 ;; # optional
@@ -174,6 +181,11 @@ if [[ -z $printGeotiff ]]; then
   printGeotiff=true
 fi
 
+# if $includeNA is not triggered
+if [[ -z $includeNA ]]; then
+  includeNA=false
+fi
+
 # check the value of $printGeotiff
 if [[ -n $printGeotiff ]]; then
   case "${printGeotiff,,}" in
@@ -254,6 +266,7 @@ declare -A funcArgs=([geotiffDir]="$geotiffDir" \
 		     [jobSubmission]="$jobSubmission" \
 		     [printGeotiff]="$printGeotiff" \
 		     [stats]="$stats" \
+		     [includeNA]="$includeNA" \
 		     [quantiles]="$quantiles" \
 		     [prefixStr]="$prefixStr" \
 		     [cache]="$cache" \
@@ -274,13 +287,14 @@ call_processing_func () {
   # all processing script files must follow same input argument standard
   local scriptRun
   read -rd '' scriptRun <<- EOF
-	bash ${script} --dataset-dir="${funcArgs[geotiffDir]}" --crs="${funcArgs[crs]}" --variable="${funcArgs[variables]}" --output-dir="${funcArgs[outputDir]}" --start-date="${funcArgs[startDate]}" --end-date="${funcArgs[endDate]}" --lat-lims="${funcArgs[latLims]}" --lon-lims="${funcArgs[lonLims]}" --shape-file="${funcArgs[shapefile]}" --print-geotiff="${funcArgs[printGeotiff]}" --stat="${funcArgs[stats]}" --quantile="${funcArgs[quantiles]}" --prefix="${funcArgs[prefixStr]}" --cache="${funcArgs[cache]}"
+	bash ${script} --dataset-dir="${funcArgs[geotiffDir]}" --crs="${funcArgs[crs]}" --variable="${funcArgs[variables]}" --output-dir="${funcArgs[outputDir]}" --start-date="${funcArgs[startDate]}" --end-date="${funcArgs[endDate]}" --lat-lims="${funcArgs[latLims]}" --lon-lims="${funcArgs[lonLims]}" --shape-file="${funcArgs[shapefile]}" --print-geotiff="${funcArgs[printGeotiff]}" --stat="${funcArgs[stats]}" --include-na="${funcArgs[includeNA]}" --quantile="${funcArgs[quantiles]}" --prefix="${funcArgs[prefixStr]}" --cache="${funcArgs[cache]}"
 	EOF
 
   # evaluate the script file using the arguments provided
   if [[ "${funcArgs[jobSubmission]}" == true ]]; then
     # Create a temporary directory for keeping job logs
-    mkdir -p "$HOME/scratch/.gdt_logs"
+    logDir="$HOME/scratch/.gistool_logs/"
+    mkdir -p "$logDir" 
     # SLURM batch file
     sbatch <<- EOF
 	#!/bin/bash
@@ -290,15 +304,15 @@ call_processing_func () {
 	#SBATCH --time=04:00:00
 	#SBATCH --mem=16GB
 	#SBATCH --job-name=GIS_${scriptName}
-	#SBATCH --error=$HOME/scratch/.gdt_logs/GIS_%j_err.txt
-	#SBATCH --output=$HOME/scratch/.gdt_logs/GIS_%j.txt
+	#SBATCH --error=$logDir/GIS_%j_err.txt
+	#SBATCH --output=$logDir/GIS_%j.txt
 	#SBATCH --mail-user=$email
 	#SBATCH --mail-type=BEGIN,END,FAIL
 
 	srun ${scriptRun} --cache="${cache}-\${SLURM_JOB_ID}" 
 	EOF
     # echo message
-    echo "$(basename $0): job submission details are printed under ${HOME}/scratch/.gdt_logs"
+    echo "$(basename $0): job submission details are printed under ${logDir}"
 
   else
     eval "$scriptRun"

diff --git a/gsde/gsde.sh b/gsde/gsde.sh
@@ -1,6 +1,7 @@
 #!/bin/bash
 # GIS Data Processing Workflow
-# Copyright (C) 2022, University of Saskatchewan
+# Copyright (C) 2022-2023, University of Saskatchewan
+# Copyright (C) 2023, University of Calgary
 # Copyright (C) 2021, Wouter Knoben
 #
 # This file is part of GIS Data Processing Workflow
@@ -40,12 +41,12 @@
 # Usage Functions
 # ===============
 short_usage() {
-  echo "usage: $(basename $0) -cio DIR -v var1[,var2[...]] [-r INT] [-se DATE] [-ln REAL,REAL] [-f PATH] [-t BOOL] [-a stat1[,stat2,[...]] [-q q1[,q2[...]]]] [-p STR] "
+  echo "usage: $(basename $0) -cio DIR -v var1[,var2[...]] [-r INT] [-se DATE] [-ln REAL,REAL] [-f PATH] [-t BOOL] [-a stat1[,stat2,[...]] [-u BOOL] [-q q1[,q2[...]]]] [-p STR] "
 }
 
 
 # argument parsing using getopt - WORKS ONLY ON LINUX BY DEFAULT
-parsedArguments=$(getopt -a -n gsde -o i:o:v:r:s:e:l:n:f:t:a:q:p:c: --long dataset-dir:,output-dir:,variable:,crs:,start-date:,end-date:,lat-lims:,lon-lims:,shape-file:,print-geotiff:,stat:,quantile:,prefix:,cache: -- "$@")
+parsedArguments=$(getopt -a -n gsde -o i:o:v:r:s:e:l:n:f:t:a:u:q:p:c: --long dataset-dir:,output-dir:,variable:,crs:,start-date:,end-date:,lat-lims:,lon-lims:,shape-file:,print-geotiff:,stat:,include-na:,quantile:,prefix:,cache: -- "$@")
 validArguments=$?
 if [ "$validArguments" != "0" ]; then
   short_usage;
@@ -74,6 +75,7 @@ do
     -f | --shape-file)    shapefile="$2"       ; shift 2 ;; # required - could be redundant
     -t | --print-geotiff) printGeotiff="$2"    ; shift 2 ;; # required
     -a | --stat)	  stats="$2"	       ; shift 2 ;; # optional
+    -u | --include-na)	  includeNA="$2"       ; shift 2 ;; # required
     -q | --quantile)	  quantiles="$2"       ; shift 2 ;; # optional
     -p | --prefix)	  prefix="$2"          ; shift 2 ;; # optional
     -c | --cache)	  cache="$2"           ; shift 2 ;; # required
@@ -284,6 +286,7 @@ if [[ -n "$shapefile" ]] && [[ -n $stats ]]; then
 	    "$shapefile" \
 	    "$outputDir/${prefix}stats_${var}.csv" \
 	    "$stats" \
+	    "$includeNA" \ 
 	    "$quantiles" >> "${outputDir}/${prefix}stats_${var}.log" 2>&1;
   done
 fi

diff --git a/landsat/landsat.sh b/landsat/landsat.sh
@@ -41,12 +41,12 @@
 # Usage Functions
 # ===============
 short_usage() {
-  echo "usage: $(basename $0) -cio DIR -v var1[,var2[...]] [-r INT] [-se DATE] [-ln REAL,REAL] [-f PATH] [-t BOOL] [-a stat1[,stat2,[...]] [-q q1[,q2[...]]]] [-p STR] "
+  echo "usage: $(basename $0) -cio DIR -v var1[,var2[...]] [-r INT] [-se DATE] [-ln REAL,REAL] [-f PATH] [-t BOOL] [-a stat1[,stat2,[...]] [-u BOOL] [-q q1[,q2[...]]]] [-p STR] "
 }
 
 
 # argument parsing using getopt - WORKS ONLY ON LINUX BY DEFAULT
-parsedArguments=$(getopt -a -n landsat -o i:o:v:r:s:e:l:n:f:t:a:q:p:c: --long dataset-dir:,output-dir:,variable:,crs:,start-date:,end-date:,lat-lims:,lon-lims:,shape-file:,print-geotiff:,stat:,quantile:,prefix:,cache: -- "$@")
+parsedArguments=$(getopt -a -n landsat -o i:o:v:r:s:e:l:n:f:t:a:u:q:p:c: --long dataset-dir:,output-dir:,variable:,crs:,start-date:,end-date:,lat-lims:,lon-lims:,shape-file:,print-geotiff:,stat:,include-na:,quantile:,prefix:,cache: -- "$@")
 validArguments=$?
 if [ "$validArguments" != "0" ]; then
   short_usage;
@@ -75,6 +75,7 @@ do
     -f | --shape-file)    shapefile="$2"       ; shift 2 ;; # required - could be redundant
     -t | --print-geotiff) printGeotiff="$2"    ; shift 2 ;; # required
     -a | --stat)	  stats="$2"	       ; shift 2 ;; # optional
+    -u | --include-na)	  includeNA="$2"       ; shift 2 ;; # required
     -q | --quantile)	  quantiles="$2"       ; shift 2 ;; # optional
     -p | --prefix)	  prefix="$2"          ; shift 2 ;; # optional
     -c | --cache)	  cache="$2"           ; shift 2 ;; # required
@@ -385,7 +386,8 @@ if [[ -n "$shapefile" ]] && [[ -n $stats ]]; then
 	    "$shapefile" \
 	    "$outputDir/${prefix}stats_${fileName[0]}.csv" \
 	    "$stats" \
-	    "$quantiles" >> "${outputDir}/${prefix}stats_${fileName[0]}.log" 2>&1;
+	    "$includeNA" \
+	    "$quantiles" >> "${outputDir}/${prefix}stats_${fileName[0]}.log" 2>&1; 
     wait;
   done
 fi

diff --git a/merit_hydro/merit_hydro.sh b/merit_hydro/merit_hydro.sh
@@ -43,12 +43,12 @@
 # Usage Functions
 # ===============
 short_usage() {
-  echo "usage: $(basename $0) -cio DIR -v var1[,var2[...]] [-r INT] [-se DATE] [-ln REAL,REAL] [-f PATH] [-t BOOL] [-a stat1[,stat2,[...]] [-q q1[,q2[...]]]] [-p STR] "
+  echo "usage: $(basename $0) -cio DIR -v var1[,var2[...]] [-r INT] [-se DATE] [-ln REAL,REAL] [-f PATH] [-t BOOL] [-a stat1[,stat2,[...]] [-u BOOL] [-q q1[,q2[...]]]] [-p STR] "
 }
 
 
 # argument parsing using getopt - WORKS ONLY ON LINUX BY DEFAULT
-parsedArguments=$(getopt -a -n merit_hydro -o i:o:v:r:s:e:l:n:f:t:a:q:p:c: --long dataset-dir:,output-dir:,variable:,crs:,start-date:,end-date:,lat-lims:,lon-lims:,shape-file:,print-geotiff:,stat:,quantile:,prefix:,cache: -- "$@")
+parsedArguments=$(getopt -a -n merit_hydro -o i:o:v:r:s:e:l:n:f:t:a:u:q:p:c: --long dataset-dir:,output-dir:,variable:,crs:,start-date:,end-date:,lat-lims:,lon-lims:,shape-file:,print-geotiff:,stat:,include-na:,quantile:,prefix:,cache: -- "$@")
 validArguments=$?
 if [ "$validArguments" != "0" ]; then
   short_usage;
@@ -376,6 +376,7 @@ if [[ -n "$shapefile" ]] && [[ -n $stats ]]; then
 	    "$shapefile" \
 	    "$outputDir/${prefix}stats_${var}.csv" \
 	    "$stats" \
+	    "$includeNA" \ 
 	    "$quantiles" >> "${outputDir}/${prefix}stats_${var}.log" 2>&1;
   done
 fi

diff --git a/modis/modis.sh b/modis/modis.sh
@@ -41,12 +41,12 @@
 # Usage Functions
 # ===============
 short_usage() {
-  echo "usage: $(basename $0) -cio DIR -v var1[,var2[...]] [-r INT] [-se DATE] [-ln REAL,REAL] [-f PATH] [-t BOOL] [-a stat1[,stat2,[...]] [-q q1[,q2[...]]]] [-p STR] "
+  echo "usage: $(basename $0) -cio DIR -v var1[,var2[...]] [-r INT] [-se DATE] [-ln REAL,REAL] [-f PATH] [-t BOOL] [-a stat1[,stat2,[...]] [-u BOOL] [-q q1[,q2[...]]]] [-p STR] "
 }
 
 
 # argument parsing using getopt - WORKS ONLY ON LINUX BY DEFAULT
-parsedArguments=$(getopt -a -n modis -o i:o:v:r:s:e:l:n:f:t:a:q:p:c: --long dataset-dir:,output-dir:,variable:,crs:,start-date:,end-date:,lat-lims:,lon-lims:,shape-file:,print-geotiff:,stat:,quantile:,prefix:,cache: -- "$@")
+parsedArguments=$(getopt -a -n modis -o i:o:v:r:s:e:l:n:f:t:a:u:q:p:c: --long dataset-dir:,output-dir:,variable:,crs:,start-date:,end-date:,lat-lims:,lon-lims:,shape-file:,print-geotiff:,stat:,include-na:,quantile:,prefix:,cache: -- "$@")
 validArguments=$?
 if [ "$validArguments" != "0" ]; then
   short_usage;
@@ -75,6 +75,7 @@ do
     -f | --shape-file)    shapefile="$2"       ; shift 2 ;; # required - could be redundant
     -t | --print-geotiff) printGeotiff="$2"    ; shift 2 ;; # required
     -a | --stat)	  stats="$2"	       ; shift 2 ;; # optional
+    -u | --include-na)    includeNA="$2"       ; shift 2 ;; # required
     -q | --quantile)	  quantiles="$2"       ; shift 2 ;; # optional
     -p | --prefix)	  prefix="$2"          ; shift 2 ;; # optional
     -c | --cache)	  cache="$2"           ; shift 2 ;; # required
@@ -314,6 +315,7 @@ if [[ -n "$shapefile" ]] && [[ -n $stats ]]; then
 	      "$shapefile" \
 	      "$outputDir/${var}/${prefix}stats_${var}_${yr}.csv" \
 	      "$stats" \
+	      "$includeNA" \ 
 	      "$quantiles" >> "${outputDir}/${var}/${prefix}stats_${var}_${yr}.log" 2>&1;
     done
   done

diff --git a/soil_grids/soil_grids_v1.sh b/soil_grids/soil_grids_v1.sh
@@ -4,7 +4,7 @@
 # Copyright (C) 2022-2023, University of Saskatchewan
 # Copyright (C) 2023, University of Calgary
 #
-# This file is part of GIS Data Processing Workflow
+# This file is part of Geospatial Data Processing Workflow
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -41,12 +41,12 @@
 # Usage Functions
 # ===============
 short_usage() {
-  echo "usage: $(basename $0) -cio DIR -v var1[,var2[...]] [-r INT] [-se DATE] [-ln REAL,REAL] [-f PATH] [-t BOOL] [-a stat1[,stat2,[...]] [-q q1[,q2[...]]]] [-p STR] "
+  echo "usage: $(basename $0) -cio DIR -v var1[,var2[...]] [-r INT] [-se DATE] [-ln REAL,REAL] [-f PATH] [-t BOOL] [-a stat1[,stat2,[...]] [-u BOOL] [-q q1[,q2[...]]]] [-p STR] "
 }
 
 
 # argument parsing using getopt - WORKS ONLY ON LINUX BY DEFAULT
-parsedArguments=$(getopt -a -n soil-grids-v1 -o i:o:v:r:s:e:l:n:f:t:a:q:p:c: --long dataset-dir:,output-dir:,variable:,crs:,start-date:,end-date:,lat-lims:,lon-lims:,shape-file:,print-geotiff:,stat:,quantile:,prefix:,cache: -- "$@")
+parsedArguments=$(getopt -a -n soil-grids-v1 -o i:o:v:r:s:e:l:n:f:t:a:u:q:p:c: --long dataset-dir:,output-dir:,variable:,crs:,start-date:,end-date:,lat-lims:,lon-lims:,shape-file:,print-geotiff:,stat:,include-na:,quantile:,prefix:,cache: -- "$@")
 validArguments=$?
 if [ "$validArguments" != "0" ]; then
   short_usage;
@@ -75,6 +75,7 @@ do
     -f | --shape-file)    shapefile="$2"       ; shift 2 ;; # required - could be redundant
     -t | --print-geotiff) printGeotiff="$2"    ; shift 2 ;; # required
     -a | --stat)	  stats="$2"	       ; shift 2 ;; # optional
+    -u | --include-na)    includeNA="$2"       ; shift 2 ;; # required
     -q | --quantile)	  quantiles="$2"       ; shift 2 ;; # optional
     -p | --prefix)	  prefix="$2"          ; shift 2 ;; # optional
     -c | --cache)	  cache="$2"           ; shift 2 ;; # required
@@ -272,6 +273,7 @@ if [[ -n "$shapefile" ]] && [[ -n $stats ]]; then
 	    "$shapefile" \
 	    "$outputDir/${prefix}stats_${var}.csv" \
 	    "$stats" \
+	    "$includeNA" \ 
 	    "$quantiles" >> "${outputDir}/${prefix}stats_${var}.log" 2>&1;
   done
 fi